专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明专利

JP2014049112A Information processing device, program, and job control method 有权
标题翻译：信息处理设备，程序和作业控制方法
公开(公告)号：JP2014049112A
公开(公告)日：2014-03-17
申请号：JP2012251411
申请日：2012-11-15
申请人： Fujitsu Ltd , 富士通株式会社 , Georgia Tech Research Corp , ジョージア・テック・リサーチ・コーポレーション
发明人： KANEMASA YASUHIKO , KAWABA MOTOYUKI , PU CARTON , WANG JING YANG
IPC分类号： G06F9/48
CPC分类号： G06F9/4881 , G06F2209/485 , G06F2209/486
摘要： PROBLEM TO BE SOLVED: To provide an information processing device which suppresses violent fluctuations in a response time.SOLUTION: An information processing device classifies jobs to be executed by a server 4 into a plurality of groups, and ranks the groups in ascending order of workload to be imposed on the server 4 by the jobs belonging to the group. Counting means 1f counts the number of jobs which are being executed by the server 4 and also belong to the predetermined number of top-ranked groups. Inhibition means 1g determines processing requests of jobs belonging to the groups other than the predetermined number of top-ranked groups as inhibition targets, and inhibits the inhibition target processing requests from being transmitted to the server 4, when the number of counted jobs are equal to or more than a predetermined threshold and also there are jobs which belong to the predetermined number of top-ranked groups and are waiting to be processed.
摘要翻译：要解决的问题：提供一种抑制响应时间的剧烈波动的信息处理装置。解决方案：信息处理装置将由服务器4执行的作业分类成多个组，并以工作量的升序对组进行排序由属于该组的作业施加在服务器4上。计数装置1f计算由服务器4执行的作业的数目，并且也属于预定数量的顶级组。抑制单元1g确定属于除预定数量的顶级组之外的组的作业的处理请求作为禁止目标，并且当计数作业的数目等于...时禁止向服务器4发送禁止目标处理请求或大于预定阈值，并且还存在属于预定数量的顶级组并且正在等待被处理的作业。

2. 发明专利

JP2012083918A Information processing program, device and method 有权
标题翻译：信息处理程序，设备和方法
公开(公告)号：JP2012083918A
公开(公告)日：2012-04-26
申请号：JP2010228982
申请日：2010-10-08
申请人： Fujitsu Ltd , 富士通株式会社
发明人： KAWABA MOTOYUKI
IPC分类号： G06F11/34 , G06F15/00
CPC分类号： H04L51/22 , G06F17/30587
摘要： PROBLEM TO BE SOLVED: To identify, in messages that are not associated with other messages, a candidate of an association key for associating the messages with other messages.SOLUTION: An information processing method includes: a step of extracting messages including attribute values of a first attribute and the appearance time of each message from a message storage unit for storing messages including attribute values of one or plural attributes and the appearance time of each message associated with each other; a step of using the extracted data to calculate, for each attribute value of the first attribute, an existing period that is a difference between the earliest appearance time and the latest appearance time among the appearance time of the messages including the attribute value; a step of determining whether a rate of the existing period shorter than a predetermined period to the calculated existing periods is equal to or more than a predetermined threshold; and a step of storing data indicating that the first attribute is a candidate of an association key in a data storage unit when it is determined that the rate is equal to or more than the predetermined threshold.
摘要翻译：要解决的问题：为了在不与其他消息相关联的消息中识别用于将消息与其他消息相关联的关联密钥的候选。解决方案：一种信息处理方法，包括：从包含一个或多个属性的属性值的消息的消息存储单元中提取包括第一属性的属性值和每个消息的出现时间的消息的步骤，以及出现时间每个消息相互关联; 对于所述第一属性的每个属性值，在包括所述属性值的消息的出现时间之间，使用所提取的数据来计算作为所述最早出现时间与最近出现时间之间的差的现有期间的步骤; 确定比计算的现有周期短于预定周期的现有周期的速率是否等于或大于预定阈值的步骤; 以及当确定所述速率等于或大于所述预定阈值时，将指示所述第一属性是关联密钥的候选的数据存储在数据存储单元中的步骤。版权所有（C）2012，JPO＆INPIT

3. 发明专利

JP2009282807A Apparatus, method and program for message binding processing 有权
标题翻译：用于信息绑定处理的装置，方法和程序
公开(公告)号：JP2009282807A
公开(公告)日：2009-12-03
申请号：JP2008135002
申请日：2008-05-23
申请人： Fujitsu Ltd , 富士通株式会社
发明人： HOTTA YUJI , KAWABA MOTOYUKI , TAKAHASHI HIDEKAZU , HARADA RIRIAN
IPC分类号： G06F9/50
CPC分类号： G06F9/546
摘要： PROBLEM TO BE SOLVED: To thoroughly perform binding processing when dynamically adding or stopping a server or the like for performing message binding processing.
SOLUTION: A message binding processing apparatus includes: a receiving means which receives a plurality of messages related to a plurality of transactions in random order; a plurality of binding processing means each of which classifies messages in a queue for storing messages related to a transaction in charge for each transaction, and then outputting the messages to a message processing part; a message distribution means which outputs received messages to any one of the binding processing means, which is specified by a transaction identifier of the messages and a distribution rule predetermined about the transaction identifier; and a configuration changing means for changing the distribution rule when the binding processing means is started or stopped. When the configuration changing means changes the distribution rule, each binding processing means outputs the messages stored in the queue to the message distribution means.
COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：在动态添加或停止用于执行消息绑定处理的服务器等时彻底地执行绑定处理。解决方案：消息绑定处理装置包括：接收装置，其以随机顺序接收与多个事务相关的多个消息; 多个装订处理装置，其中每一个将队列中的消息分类以存储与每个交易负责的交易有关的消息，然后将消息输出到消息处理部分; 将接收到的消息输出到由消息的事务标识符指定的绑定处理装置中的接收消息和关于事务标识符预先分配的分发规则的消息分发装置; 以及配置改变装置，用于当装订处理装置启动或停止时改变分配规则。当配置改变装置改变分配规则时，每个装订处理装置将存储在队列中的消息输出到消息分发装置。版权所有（C）2010，JPO＆INPIT

4. 发明专利

JP2009238069A Linkage support apparatus and linkage support method 有权
标题翻译：链接支持设备和链接支持方法
公开(公告)号：JP2009238069A
公开(公告)日：2009-10-15
申请号：JP2008085372
申请日：2008-03-28
申请人： Fujitsu Ltd , 富士通株式会社
发明人： KAWABA MOTOYUKI , TAKAHASHI HIDEKAZU , HOTTA YUJI , HARADA RIRIAN
IPC分类号： G06F15/00 , G06F13/00
CPC分类号： G06F9/546
摘要： PROBLEM TO BE SOLVED: To provide a technology for supporting automatic design of a linkage system capable of carrying out linkage processing of high efficiency. SOLUTION: This linkage support apparatus for supporting linkage processing of linking mutually related messages in a plurality of messages sent and received among a plurality of communication terminals, comprises an information acquisition unit for acquiring the respective message types of the plurality of messages, character strings included in the plurality of messages, and the amount of data flow when the character strings are transferred; an unnecessary character string exclusion unit for excluding character strings unnecessary as keywords for linkage processing, out of a plurality of character strings acquired by the information acquisition unit, based on the information acquired by the information acquisition unit; and a processing order determination unit for determining order for using the plurality of character strings from which the unnecessary character strings are excluded by the unnecessary character string exclusion unit, in linkage processing based on the information acquired by the information acquisition unit. COPYRIGHT: (C)2010,JPO&INPIT
摘要翻译：要解决的问题：提供一种支持自动设计能够执行高效率的联动处理的联动系统的技术。解决方案：用于支持在多个通信终端之间发送和接收的多个消息中链接相互关联的消息的链接处理的联动支持装置包括：信息获取单元，用于获取多个消息的各个消息类型; 包括在多个消息中的字符串以及当字符串被传送时的数据流量; 一个不必要的字符串排除单元，用于根据由信息获取单元获取的信息，排除由信息获取单元获取的多个字符串中不必要的用于链接处理的关键字的字符串; 以及处理顺序确定单元，用于基于由信息获取单元获取的信息进行联动处理，确定使用由不需要的字符串排除单元排除不需要的字符串的多个字符串的顺序。版权所有（C）2010，JPO＆INPIT

5. 发明专利

JP2013097783A Program, analysis method, and information processor 有权
标题翻译：程序，分析方法和信息处理器
公开(公告)号：JP2013097783A
公开(公告)日：2013-05-20
申请号：JP2012026293
申请日：2012-02-09
申请人： Fujitsu Ltd , 富士通株式会社 , Georgia Tech Research Corp , ジョージア・テック・リサーチ・コーポレーション
发明人： KANEMASA YASUHIKO , KAWABA MOTOYUKI , PU CARTON , WANG JING YANG
IPC分类号： G06F11/34
CPC分类号： G06F11/3419 , G06F11/323 , G06F11/3442 , G06F11/3452 , G06F11/3495 , G06F2201/875
摘要： PROBLEM TO BE SOLVED: To determine presence/absence of surplus of throughput of an analysis object device.SOLUTION: Calculation means 1c acquires information indicating an execution period of processing executed within an analysis object period in the analysis object device, from storage means 1b. Then, the calculation means 1c calculates the total processing time obtained by totalling the time consumed for execution of respective processing executed within a sum-up section for each sum-up section obtained by subdividing the analysis object period. Also, the calculation means 1c calculates the total advance amount obtained by totalling advance amounts of the respective processing executed within the sum-up section for each sum-up section. Determination means 1d determines a threshold of the total processing time at which an increase amount of the total advance amount to an increase amount of the total processing time becomes equal to or smaller than a prescribed value on the basis of the total processing time and the total advance amount of each sum-up section. Then, detection means 1e detects the sum-up section in which the total processing time is equal to or greater than the threshold.
摘要翻译：要解决的问题：确定分析对象设备的吞吐量过剩的存在/不存在。解决方案：计算装置1c从存储装置1b获取指示在分析对象装置内的分析对象周期内执行的处理的执行周期的信息。然后，计算装置1c计算通过对通过细分分析对象期间而获得的各个总计部分的总计部分内执行的各个处理所消耗的时间进行合计而获得的总处理时间。此外，计算单元1c计算通过对于每个总计部分合计在总计部分内执行的各个处理的预先金额而获得的总预付金额。确定装置1d基于总处理时间和总共处理时间确定总处理时间的增加量与总处理时间的增加量等于或小于规定值的总处理时间的阈值每个总结部分的预付金额。然后，检测装置1e检测总处理时间等于或大于阈值的总和部分。版权所有（C）2013，JPO＆INPIT

6. 发明专利

JP2012194604A Information processor, message classification method, and message classification program 有权
标题翻译：信息处理器，消息分类方法和消息分类程序
公开(公告)号：JP2012194604A
公开(公告)日：2012-10-11
申请号：JP2011055967
申请日：2011-03-14
申请人： Fujitsu Ltd , 富士通株式会社
发明人： HOTTA YUJI , KAWABA MOTOYUKI
IPC分类号： G06F11/34
CPC分类号： G06F11/3495 , G06F11/3419 , G06F11/3476 , G06F2201/865 , G06F2201/87 , G06F2201/875
摘要： PROBLEM TO BE SOLVED: To associate a series of transactions.SOLUTION: An association server has a first storage unit for storing occurrence patterns of messages having transaction identifiers for identifying transactions. Also, the association server has a second storage unit for storing messages generated between an application server and a DB server when the application server has caused the DB server to execute transactions having transaction IDs. Then, based on the occurrence patterns of messages stored in the first storage unit, the association server classifies messages stored in the second storage unit by transactions.
摘要翻译：要解决的问题：关联一系列交易。解决方案：关联服务器具有第一存储单元，用于存储具有用于识别事务的事务标识符的消息的发生模式。此外，关联服务器具有第二存储单元，用于当应用服务器使DB服务器执行具有事务ID的事务时，存储在应用服务器和DB服务器之间生成的消息。然后，基于存储在第一存储单元中的消息的发生模式，关联服务器通过事务对存储在第二存储单元中的消息进行分类。版权所有（C）2013，JPO＆INPIT

7. 发明专利

JP2011244164A Server abnormality determination program, server abnormality determination device and server abnormality determination method 审中-公开
标题翻译：服务器异常确定程序，服务器异常确定设备和服务器异常确定方法
公开(公告)号：JP2011244164A
公开(公告)日：2011-12-01
申请号：JP2010113847
申请日：2010-05-18
申请人： Fujitsu Ltd , 富士通株式会社
发明人： HOTTA YUJI , KAWABA MOTOYUKI , TAKAHASHI HIDEKAZU
IPC分类号： G06F13/00 , H04L12/24 , H04L12/26 , H04L12/70
摘要： PROBLEM TO BE SOLVED: To identify a server that is the cause of a fault.SOLUTION: A server abnormality determination device stores information identifying a server, routing information showing a route including the server regarding message data of a transaction, and information associated with a server response average that is an average of response values, each of which represents a time from sending of a request message for the transaction to reception of an answer message in the server. When the server response average is greater than a threshold, the server abnormality determination device determines that an abnormality has occurred in the route, and records the information identifying the server and the routing information.
摘要翻译：要解决的问题：识别出现故障原因的服务器。解决方案：服务器异常确定装置存储识别服务器的信息，示出包括关于交易的消息数据的服务器的路线的路由信息，以及与作为响应值的平均值的服务器响应平均值相关联的信息，表示从服务器发送用于该事务的请求消息到接收答复消息的时间。当服务器响应平均值大于阈值时，服务器异常判定装置判定路径中发生异常，记录识别服务器的信息和路由信息。版权所有（C）2012，JPO＆INPIT

8. 发明专利

JP2011053919A Parallel linking processing system and method 有权
标题翻译：并行连接处理系统及方法
公开(公告)号：JP2011053919A
公开(公告)日：2011-03-17
申请号：JP2009202305
申请日：2009-09-02
申请人： Fujitsu Ltd , 富士通株式会社
发明人： KAWABA MOTOYUKI
IPC分类号： G06F15/00
CPC分类号： H04L12/66
摘要： PROBLEM TO BE SOLVED: To collect unlinked messages in a state that a response to a request is not returned. SOLUTION: In a system including a plurality of linking processing parts to perform the linking processing of related messages in parallel, the plurality of linking processing parts mutually exchange a plurality of combinations of key character strings and values included in a message group of not only received messages in charge but also unlinked messages to be linked, store the exchanged combinations in a trace data storage part, and extract other combinations related to a specific combination of a key character string and a value specified from a noticed message. By extracting messages related to the extracted combinations from the corresponding linking processing part, unlinked messages to be noticed are extracted and a problem or the like can be analyzed. COPYRIGHT: (C)2011,JPO&INPIT
摘要翻译：要解决的问题：在不返回对请求的响应的状态下收集未链接的消息。解决方案：在包括并行执行相关消息的链接处理的多个链接处理部分的系统中，多个链接处理部分相互交换密钥字符串的多个组合以及包括在消息组不仅收到负责的消息，还收到要链接的未链接消息，将交换的组合存储在跟踪数据存储部分中，并提取与密钥字符串的特定组合和从注意到的消息指定的值相关的其他组合。通过从相应的链接处理部分提取与提取的组合相关的消息，提取要注意的未链接的消息，并且可以分析问题等。版权所有（C）2011，JPO＆INPIT

9. 发明专利

JP2004078338A Method and system for evaluating computer performance 审中-公开
标题翻译：用于评估计算机性能的方法和系统
公开(公告)号：JP2004078338A
公开(公告)日：2004-03-11
申请号：JP2002234536
申请日：2002-08-12
申请人： Fujitsu Ltd , 富士通株式会社
发明人： KAWABA MOTOYUKI
IPC分类号： G06F11/34
摘要： PROBLEM TO BE SOLVED: To easily determine a sampling trace length suitable for the extraction of a representative trace by clustering in a computer performance evaluation method.
SOLUTION: This computer performance evaluation method uses the representative sampling trace obtained by sampling from the execution history of a program. Based on the total number of execution instructions when an objective program is run and specified measurement information, the number of variations in the behaviors of the program when the program is run is calculated and, based on the total number of the execution instructions and the number of variations when the program is run is calculated. Based on the total number of the execution instructions and the number of variations in the behavior, the trace length of the sampled sampling trace is calculated, the sampling trace is sampled from the objective program based on the trace length, the sampled sampling trace is clustered, and the representative sampling trace is determined for each cluster.
COPYRIGHT: (C)2004,JPO
摘要翻译：要解决的问题：通过在计算机性能评估方法中聚类，容易地确定适合于提取代表性迹线的采样迹线长度。
解决方案：该计算机性能评估方法使用通过从程序的执行历史进行抽样获得的代表性采样跟踪。基于运行目标程序时的执行指令总数和指定的测量信息，计算程序运行时程序行为的变化次数，并根据执行指令的总数和编号计算运行程序时的变化。根据执行指令的总数和行为的变化次数，计算采样采样跟踪的跟踪长度，根据跟踪长度从目标程序采样采样跟踪，采样采样跟踪集群，并为每个集群确定代表性采样跟踪。版权所有（C）2004，JPO

10. 发明专利

JP2014232348A ストレージシステム、情報処理装置の制御プログラム、およびストレージシステムの制御方法有权
标题翻译：存储系统，信息处理设备的控制程序和存储系统的控制方法
公开(公告)号：JP2014232348A
公开(公告)日：2014-12-11
申请号：JP2013111674
申请日：2013-05-28
申请人：富士通株式会社 , Fujitsu Ltd
发明人： OGIWARA KAZUTAKA , OE KAZUICHI , KAWABA MOTOYUKI
IPC分类号： G06F3/06
CPC分类号： G06F3/0611 , G06F3/0649 , G06F3/0665 , G06F3/0685
摘要：【課題】負荷変動に対してアクセス性能を改善する。【解決手段】ストレージシステム1は、アクセス速度が遅い第1のストレージ装置2と、アクセス速度が速い第2のストレージ装置3と、情報処理装置10を備える。情報処理装置10は、仮想ボリューム4に割り当てられる割当単位領域5のアクセス頻度の変化に応じて、第1のストレージ装置2と第2のストレージ装置3とから割当単位領域5を構成することができる。評価部12は、割当単位領域5より小さなサイズの分割領域6ごとに、ユーザからのI/Oリクエストに対する評価情報を生成する。移動制御部13は、仮想ボリューム4への割当を、第1のストレージ装置2の割当単位領域5(第1の割当単位領域)から第2のストレージ装置3の割当単位領域5(第2の割当単位領域)に変更する場合、評価情報に基づいてデータを移動する。【選択図】図1
摘要翻译：要解决的问题：提高针对负载波动的访问性能。解决方案：存储系统1包括具有低访问速度的第一存储设备2，具有高访问速度的第二存储设备3和信息处理设备10.信息处理根据分配给虚拟卷4的分配单元区域5的访问频率的变化，设备10能够使用第一存储设备2和第二存储设备3来配置分配单元区域5.评估单元12生成评估信息与来自小于分配单元区域5的每个分割区域6的来自用户的I / O请求。移动控制单元13在从虚拟卷4分配到虚拟卷4的分配中基于评估信息移动数据第一存储装置2的分配单位区域5（第一分配单位区域）到第二存储装置3的分配单位区域5（第二分配单位区域 N）。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式